Updated Speechmatics STT integration #4359
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
longcw
approved these changes
Jan 5, 2026
Contributor
longcw
left a comment
longcw
left a comment
There was a problem hiding this comment.
LGTM! could you help to resolve the conflicts with the main branch. and something nit:
| prefer_current_speaker=prefer_current_speaker, | ||
| focus_speakers=focus_speakers if is_given(focus_speakers) else [], | ||
| ignore_speakers=ignore_speakers if is_given(ignore_speakers) else [], | ||
| language=_set(language), |
Contributor
There was a problem hiding this comment.
Suggested change
| language=_set(language), | |
| language=language, |
| transcription_config.language = language | ||
|
|
||
| # Prepare the config | ||
| self._config = self._prepare_config(language) |
Contributor
There was a problem hiding this comment.
stt.stream() will overwrite the self._config, what if there are multiple streams created for a single stt instance?
| group: List of SpeechFragment objects. | ||
| logger.debug(f"{event} -> {message}") | ||
|
|
||
| async def _handle_partial_segment(self, message: dict[str, Any]) -> None: |
Contributor
There was a problem hiding this comment.
it seems all these handles including the _send_frames are sync methods, there is no need to add async for them.
chenghao-mou
reviewed
Jan 5, 2026
| """Endpoint and turn detection handling mode. | ||
| How the STT engine handles the endpointing of speech. If using Pipecat's built-in endpointing, | ||
| then use `TurnDetectionMode.EXTERNAL`. |
| language=_set(language), | ||
| output_locale=_set(output_locale), | ||
| domain=_set(domain), | ||
| turn_detection_mode=_set(turn_detection_mode), |
Member
There was a problem hiding this comment.
nit: This and focus_mode do not allow None values.
| @property | ||
| def model(self) -> str: | ||
| return "unknown" | ||
| return str(self._stt_options.turn_detection_mode) if self._stt_options else "UNKNOWN" |
Member
There was a problem hiding this comment.
This is usually reserved for STT model names like Whisper, so we really don't have to change it here.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What's Changed?
Deprecation Warning
end_of_utterance_modehas been changed toturn_detection_modeto reduce ambiguityTurnDetectionMode.EXTERNAL(default) for any VAD within LiveKitTurnDetectionMode.ADAPTIVEorTurnDetectionMode.SMART_TURNto use the plugin VAD / turn detection